Machine Learning Times
Machine Learning Times
EXCLUSIVE HIGHLIGHTS
Podcast: Four Things the Machine Learning Industry Must Learn from Self-Driving Cars
    Welcome to the next episode of The Machine...
A Refresher on Continuous Versus Discrete Input Variables
 How many times have I heard that the most...
Podcast: Why Deep Learning Could Expedite the Next AI Winter
  Welcome to the next episode of The Machine Learning...
PAW Preview Video: Evan Wimpey, Director of Strategic Analytics at Elder Research
 In anticipation of his upcoming presentation at Deep Learning...
SHARE THIS:

By: Fractal Analytics
Originally published at fractalanalyticsblog

 

While heaps of big data exist in the travel sector – from how seasonality affects bookings to the types of travel packages that receive the highest conversion rates among consumers – leveraging some of the more unstructured streams into effective predictive modeling can be a challenge. Increasing profitability in this complex industry requires significant legwork on the part of businesses as well – being in the right place at the right time is essential. While many travelers do significant research on their destination and planned visit, less attention is often paid to logistics.

Travelers are likely to have a set itinerary in place, but when unforeseen circumstances complicate the intended program they may not have a contingency plan in place. The lack of backup plans can lead to stress and confusion on the part of the consumer, who may end up following the first available alternate arrangement. A travel organization’s ability to be available during this time of duress – or better yet, to use predictive strategies to have backup plans in place and swiftly executed – can engender meaningful customer interactions and get more valuable mileage out of strategic deployments.

It does take a little creativity. Here are three ways that travel companies can utilize big data and predictive analytics to be the best travel solution.

Coordinate to Be in the Right Place:
In most big cities, taxis offer a service that is often convenient for customers to the overall detriment of the taxi providers’ profitability. Traditionally, cab deployment has often been inefficient and a product of guesswork. In the last few years, companies like Uber have arrived on the scene by using data-driven decisions to predict where taxis will be needed and give the job to the closest-located driver. Meru Cabs, a taxi company in India, uses geolocation data and other service information to better interact with drivers in the field, Business Standard contributor Shivani Shinde Nadhe wrote. They can better predict when cabs will be able to arrive at a destination and offer prospective customers more accurate information. These strategies enabled Meru to reduce its cancelation rate from 5-6 percent to just 3 percent. The organization’s customer loyalty rose nearly 20 percentage points, and drivers have been able to increase their revenue by 30 percent to 40 percent as a result.

Improve Multichannel Correspondence
Many consumers use a variety of different communication channels when making travel arrangements. They may do research online, book on the phone and correspond over email before they arrive. Consistency and credibility are important components of multichannel interaction for travel companies, as customers are often picky about logistical arrangements and apt to avoid a company they perceive to be inconsistent in its approach. More people now make arrangements online – according to Hotel News Resource, about 80 percent of consumers do. A majority of people like to receive reminders for their travel arrangements or updates to itineraries. Predicting how certain customers will utilize communication channels is a valuable predictive approach.

Predict Where Customers Will Have the Best Experience
One thing that does complicate many travel services is the deluge of social information, a side effect of travelers’ eagerness to share their thoughts and experiences with others. As a result, many consumers can feel overwhelmed by seemingly limitless options, and when many services have positive reviews, it can be difficult for a consumer to discern what they actually want to do. This sentiment offers an opportunity for travel companies to turn their predictive modeling into prescriptive analytics, according to InformationWeek contributor Douglas Gray. A business can keep track of aspects of a particular consumer’s activity, such as where they stayed, what they did and what they ate – as well as reviews of their activities. This information can be used in-trip or in future vacations to offer targeted suggestions to customers or predict how they would enjoy a particular experience they are considering.

By: Fractal Analytics
Originally published at fractalanalyticsblog.

Leave a Reply